Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1445 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.4654. Min Act: -0.1700

Data Index: 6253888 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.4101. Min Act: -0.1700

Data Index: 3510800 (Open Web Text)

Max Activating Token Index: 298

Text #2

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.3353. Min Act: -0.1700

Data Index: 7491264 (Open Web Text)

Max Activating Token Index: 995

Text #3

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.3202. Min Act: -0.1700

Data Index: 5991096 (Open Web Text)

Max Activating Token Index: 211

Text #4

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.2692. Min Act: -0.1700

Data Index: 4493305 (Open Web Text)

Max Activating Token Index: 586

Text #5

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.2840. Min Act: -0.1700

Data Index: 2032195 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.2528. Min Act: -0.1700

Data Index: 8678637 (Open Web Text)

Max Activating Token Index: 803

Text #7

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.2255. Min Act: -0.1700

Data Index: 6903716 (Open Web Text)

Max Activating Token Index: 633

Text #8

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.2290. Min Act: -0.1700

Data Index: 4773884 (Open Web Text)

Max Activating Token Index: 683

Text #9

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.2368. Min Act: -0.1700

Data Index: 6855069 (Open Web Text)

Max Activating Token Index: 699

Text #10

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.2413. Min Act: -0.1700

Data Index: 3910372 (Open Web Text)

Max Activating Token Index: 822

Text #11

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.2100. Min Act: -0.1700

Data Index: 8497629 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.1836. Min Act: -0.1700

Data Index: 3399316 (Open Web Text)

Max Activating Token Index: 589

Text #13

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.1755. Min Act: -0.1700

Data Index: 6000080 (Open Web Text)

Max Activating Token Index: 551

Text #14

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.1594. Min Act: -0.1700

Data Index: 4569298 (Open Web Text)

Max Activating Token Index: 816

Text #15

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.1820. Min Act: -0.1700

Data Index: 7896051 (Open Web Text)

Max Activating Token Index: 600

Text #16

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.1316. Min Act: -0.1700

Data Index: 5241266 (Open Web Text)

Max Activating Token Index: 30

Text #17

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.1343. Min Act: -0.1700

Data Index: 1789759 (Open Web Text)

Max Activating Token Index: 723

Text #18

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.1037. Min Act: -0.1700

Data Index: 1155414 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 4.4654. Min Range: -4.4654

Max Act: 4.1066. Min Act: -0.1700

Data Index: 1789757 (Open Web Text)

Max Activating Token Index: 297